A facility for automated modelling of the cutting process for a particular material to be cut by a beam cutting tool, such as a waterjet cutting system, from empirical data to predict aspects of the waterjet's effect on the workpiece across a range of material thicknesses, across a range of cutting geometries, and across a range of cutting quality levels, all of which may be broader than, and independent of the actual requirements for a target workpiece, is described.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method in a computing system for constructing a waterjet cutting model, the method comprising: establishing a set of active cutting test observations; over time, receiving instructions each to modify the set of active cutting test observations; over time, receiving a plurality of waterjet cutting model generation requests; for each of the received waterjet cutting model generation requests, generating a waterjet cutting model based upon cutting test observations among all of the cutting test observations that are present in the set of active cutting test observations in accordance with the instructions received as of a threshold time; using a distinguished one of the generated waterjet cutting models to construct at least one tool path for a cutting project; and causing a waterjet cutting tool to perform the cutting project in accordance with the constructed at least one tool path, wherein the method is implemented by one or more processors of the computing system.
2. The method of claim 1 wherein, for each of the received waterjet cutting model generation requests, the threshold time is a time at which the waterjet cutting model generation request is received.
3. The method of claim 1 wherein, for each of the received waterjet cutting model generation requests, the threshold time is earlier than a time at which the waterjet cutting model generation request is received.
4. The method of claim 1 wherein at least one of the received instructions is an instruction to add one or more cutting test observations to the set of active cutting test observations.
5. The method of claim 4 , further comprising receiving from a plurality of sources cutting test observations among the cutting test observations instructed to be added to the set of active cutting test observations.
6. The method of claim 4 wherein a received instruction to add one or more cutting test observations to the set of active cutting test observations specifies a condition for maintaining the added cutting test observations in the set of active cutting test observations.
7. The method of claim 1 wherein at least one of the received instructions is an instruction to remove one or more cutting test observations from the set of active cutting test observations.
8. The method of claim 7 wherein a received instruction to remove one or more cutting test observations from the set of active cutting test observations specifies a condition for reinstating the removed cutting test observations to the set of active cutting test observations.
9. The method of claim 1 wherein the instructions are received from a plurality of sources.
10. The method of claim 1 , further comprising maintaining sets of active cutting test observations on behalf of each of two or more customers.
11. One or more computer memories collectively storing a waterjet cutting model data structure for a material type, the data structure comprising: for each of one or more aspects of a waterjet's effect on a workpiece: information specifying a relation adapted to predict the value of the aspect based on the value of one or more independent variables, the relation having been determined using cutting test results among a collection of cutting test results that includes both cutting test results received from a first source and cutting test results received from a second source distinct from the first source, such that the contents of the data structure are applicable for use, by one or more processors, in the generation of waterjet cutting control signals that control a waterjet cutting tool for performing a cutting project using a workpiece of the material type.
12. The computer memories of claim 11 wherein a first subset of the cutting test results received from the first source were received that a first time, and a second subset of the cutting test results received from the second source that is distinct from the first subset or received at a second time that is distinct from the first time.
13. The computer memories of claim 11 wherein the collection of cutting test results omits a cutting test result received from the first source at a first time and removed from the collection of cutting test results at a second time after the first time.
14. The computer memories of claim 11 wherein the process of determining the relation using cutting test results among the collection of cutting test results considers weights attributed to at least a portion of the cutting test results of the collection, and wherein the process of determining the relation using cutting test results among the collection of cutting test results considers a weight attributed to a distinguished cutting test result among the collection at a time after the distinguished cutting test result was received from the first source.
15. The computer memories of claim 11 wherein the first source is a cutting tool customer.
16. The computer memories of claim 11 wherein the first source is a cutting tool manufacturer.
17. The computer memories of claim 11 wherein the first source is any other third party.
18. The computer memories of claim 11 wherein the first source is a party who determines the relation for at least one of the aspects.
19. The computer memories of claim 11 wherein the first source is a service provider who receives cutting test results from at least a first cutting tool customer, and wherein the relation for at least one of the aspects is determined by a second cutting tool customer distinct from the first cutting tool customer.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 16, 2014
September 26, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.